|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-pubmed |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# t5-small-finetuned-pubmed |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co./t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9754 |
|
- Rouge1: 36.7213 |
|
- Rouge2: 18.6627 |
|
- Rougel: 32.3932 |
|
- Rougelsum: 32.6819 |
|
- Gen Len: 16.9326 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 100 | 2.1324 | 29.4167 | 13.5345 | 25.6588 | 25.8099 | 17.8596 | |
|
| No log | 2.0 | 200 | 2.0319 | 34.0176 | 16.285 | 29.3676 | 29.5428 | 17.1966 | |
|
| No log | 3.0 | 300 | 1.9969 | 35.0555 | 17.1712 | 30.7931 | 30.9756 | 16.8989 | |
|
| No log | 4.0 | 400 | 1.9802 | 35.997 | 17.979 | 31.8043 | 32.1127 | 16.8539 | |
|
| 2.1897 | 5.0 | 500 | 1.9754 | 36.7213 | 18.6627 | 32.3932 | 32.6819 | 16.9326 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.12.2 |
|
- Pytorch 1.9.0+cu111 |
|
- Datasets 1.14.0 |
|
- Tokenizers 0.10.3 |
|
|
